Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.8592. Min Act: -0.1700
Data Index: 2563439 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.7654. Min Act: -0.1700
Data Index: 5424392 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.7654. Min Act: -0.1700
Data Index: 6335629 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.7342. Min Act: -0.1700
Data Index: 1168958 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.7029. Min Act: -0.1700
Data Index: 4164491 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.7029. Min Act: -0.1700
Data Index: 5022235 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.7029. Min Act: -0.1700
Data Index: 6165846 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6717. Min Act: -0.1700
Data Index: 1563705 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6404. Min Act: -0.1700
Data Index: 5067692 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6717. Min Act: -0.1700
Data Index: 238460 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6404. Min Act: -0.1700
Data Index: 2951478 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 6366824 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 1221997 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 3439618 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.5779. Min Act: -0.1700
Data Index: 1182514 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 3819034 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 4587409 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 779607 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.6092. Min Act: -0.1700
Data Index: 2573643 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8592. Min Range: -5.8592
Max Act: 5.5467. Min Act: -0.1700
Data Index: 759967 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19